A video-conditioned latent diffusion model generates mesh vertex trajectories that deform an input 3D asset into render-ready 4D animations.
Objaverse-xl: A universe of 10m+ 3d objects
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Drive Any Mesh: 4D Latent Diffusion for Mesh Deformation from Video
A video-conditioned latent diffusion model generates mesh vertex trajectories that deform an input 3D asset into render-ready 4D animations.